commit b0a03c7df1c1438a6b5a670c266b02af004f5561 Author: ModelHub XC Date: Thu Aug 13 08:49:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/FutureMa_Eva-4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ee5eae0 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,73 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text + +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +FutureMa_Eva-4B-bf16.gguf filter=lfs diff=lfs merge=lfs -text +FutureMa_Eva-4B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +FutureMa_Eva-4B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FutureMa_Eva-4B-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text +FutureMa_Eva-4B-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text +FutureMa_Eva-4B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FutureMa_Eva-4B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FutureMa_Eva-4B-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +FutureMa_Eva-4B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FutureMa_Eva-4B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +FutureMa_Eva-4B-imatrix.gguf filter=lfs diff=lfs merge=lfs -text +FutureMa_Eva-4B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +FutureMa_Eva-4B-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +FutureMa_Eva-4B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +FutureMa_Eva-4B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +FutureMa_Eva-4B-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +FutureMa_Eva-4B-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +FutureMa_Eva-4B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +FutureMa_Eva-4B-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text +FutureMa_Eva-4B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +FutureMa_Eva-4B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FutureMa_Eva-4B-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +FutureMa_Eva-4B-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text +FutureMa_Eva-4B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FutureMa_Eva-4B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/FutureMa_Eva-4B-IQ2_M.gguf b/FutureMa_Eva-4B-IQ2_M.gguf new file mode 100644 index 0000000..d897b29 --- /dev/null +++ b/FutureMa_Eva-4B-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8aceb00bcfd44a8f1496a2f2e19e045e5115e73e8a8279df190fb7550585b0f +size 1512982688 diff --git a/FutureMa_Eva-4B-IQ3_M.gguf b/FutureMa_Eva-4B-IQ3_M.gguf new file mode 100644 index 0000000..ddb0f20 --- /dev/null +++ b/FutureMa_Eva-4B-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a4338bf5799d1a5e1eff594cb0915bec56c34dbb2b75fec5bf905125690a256 +size 1962895008 diff --git a/FutureMa_Eva-4B-IQ3_XS.gguf b/FutureMa_Eva-4B-IQ3_XS.gguf new file mode 100644 index 0000000..8cd46b2 --- /dev/null +++ b/FutureMa_Eva-4B-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:112eba5e57067c57765e153e0666a550da5e485e51648a2b7ffe18757f2e8182 +size 1814374048 diff --git a/FutureMa_Eva-4B-IQ3_XXS.gguf b/FutureMa_Eva-4B-IQ3_XXS.gguf new file mode 100644 index 0000000..7dc5018 --- /dev/null +++ b/FutureMa_Eva-4B-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c47187add7f3407d9f0a5fbf0eef6e9fa7dca4d5947af4baeaea1d48faced389 +size 1670187168 diff --git a/FutureMa_Eva-4B-IQ4_NL.gguf b/FutureMa_Eva-4B-IQ4_NL.gguf new file mode 100644 index 0000000..dba71a2 --- /dev/null +++ b/FutureMa_Eva-4B-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ca8e8769e1f1b114d6bb0a7de83ff3c30f8cdec1cb415b18e36b4d07100e1d3 +size 2381342368 diff --git a/FutureMa_Eva-4B-IQ4_XS.gguf b/FutureMa_Eva-4B-IQ4_XS.gguf new file mode 100644 index 0000000..73b2b25 --- /dev/null +++ b/FutureMa_Eva-4B-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b8b79439912de51bd3a0035615232f71025f7e066a02374909681d386d20fc7 +size 2270750368 diff --git a/FutureMa_Eva-4B-Q2_K.gguf b/FutureMa_Eva-4B-Q2_K.gguf new file mode 100644 index 0000000..9208cd4 --- /dev/null +++ b/FutureMa_Eva-4B-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:677b0dcfedff4450113614bad5c647a2e5e74d11b8625bfea993da41a5d23963 +size 1669498528 diff --git a/FutureMa_Eva-4B-Q2_K_L.gguf b/FutureMa_Eva-4B-Q2_K_L.gguf new file mode 100644 index 0000000..e946dbd --- /dev/null +++ b/FutureMa_Eva-4B-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22d0a1fab5008f8354e807f2062c6f5ec4808070e8bdb1c3d7865ae8393d9533 +size 1763698848 diff --git a/FutureMa_Eva-4B-Q3_K_L.gguf b/FutureMa_Eva-4B-Q3_K_L.gguf new file mode 100644 index 0000000..6d042fb --- /dev/null +++ b/FutureMa_Eva-4B-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9a1efbbc7bfadf9984bdacd3d0f1b85cbf9b5cdcc8031692642c16b057fe3d6 +size 2239784608 diff --git a/FutureMa_Eva-4B-Q3_K_M.gguf b/FutureMa_Eva-4B-Q3_K_M.gguf new file mode 100644 index 0000000..edcdee7 --- /dev/null +++ b/FutureMa_Eva-4B-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab7a1809335068285b13bf7d70b52a5ef8adf21797523b64a9d32d430f78ad7f +size 2075616928 diff --git a/FutureMa_Eva-4B-Q3_K_S.gguf b/FutureMa_Eva-4B-Q3_K_S.gguf new file mode 100644 index 0000000..66d3084 --- /dev/null +++ b/FutureMa_Eva-4B-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6299cdf70750b419938b4f0eeb3b317604b66d05ba02ea4e619e69048dbb59b +size 1886996128 diff --git a/FutureMa_Eva-4B-Q3_K_XL.gguf b/FutureMa_Eva-4B-Q3_K_XL.gguf new file mode 100644 index 0000000..42d3d57 --- /dev/null +++ b/FutureMa_Eva-4B-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:104c8bf24d4b517c9916fe182e940f3c40a077e1c61e547440e146305c2ce459 +size 2333984928 diff --git a/FutureMa_Eva-4B-Q4_0.gguf b/FutureMa_Eva-4B-Q4_0.gguf new file mode 100644 index 0000000..4d9fbcf --- /dev/null +++ b/FutureMa_Eva-4B-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74b9431cc6e249de64286feebd57779c5226670323e8b6e46b339484403e6c9c +size 2375771808 diff --git a/FutureMa_Eva-4B-Q4_1.gguf b/FutureMa_Eva-4B-Q4_1.gguf new file mode 100644 index 0000000..8becb18 --- /dev/null +++ b/FutureMa_Eva-4B-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ef57c36e4b6ba6548b40491f067e713f835361cf4c967632cc5d7dfa89876f6 +size 2596628128 diff --git a/FutureMa_Eva-4B-Q4_K_L.gguf b/FutureMa_Eva-4B-Q4_K_L.gguf new file mode 100644 index 0000000..6b33ce8 --- /dev/null +++ b/FutureMa_Eva-4B-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:422cceaad788aa25bc636df651c1ed9971444836fe21229f8d3cf86a8c6fb0fb +size 2591479968 diff --git a/FutureMa_Eva-4B-Q4_K_M.gguf b/FutureMa_Eva-4B-Q4_K_M.gguf new file mode 100644 index 0000000..35eb5de --- /dev/null +++ b/FutureMa_Eva-4B-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db5ba57f303a399c8807341cdeb8eb0361282e3714a3f1c5639aef0d9457d601 +size 2497279648 diff --git a/FutureMa_Eva-4B-Q4_K_S.gguf b/FutureMa_Eva-4B-Q4_K_S.gguf new file mode 100644 index 0000000..e5a2ecf --- /dev/null +++ b/FutureMa_Eva-4B-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d5cd64304957b9b9a0becdf7c793e5ceff938a0721f00bbe322f2e70d99d0e7 +size 2383308448 diff --git a/FutureMa_Eva-4B-Q5_K_L.gguf b/FutureMa_Eva-4B-Q5_K_L.gguf new file mode 100644 index 0000000..d3696f8 --- /dev/null +++ b/FutureMa_Eva-4B-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b76ac32bdd7c0e55449e97bb8bf6b8b6cd2670f94be84cf7e64407081eee23a +size 2983712928 diff --git a/FutureMa_Eva-4B-Q5_K_M.gguf b/FutureMa_Eva-4B-Q5_K_M.gguf new file mode 100644 index 0000000..419c0dc --- /dev/null +++ b/FutureMa_Eva-4B-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:467a39ab9b05f957c5e476b750b6b633235a093f1513eda3d6898c1dd9f7514a +size 2889512608 diff --git a/FutureMa_Eva-4B-Q5_K_S.gguf b/FutureMa_Eva-4B-Q5_K_S.gguf new file mode 100644 index 0000000..c68d8dd --- /dev/null +++ b/FutureMa_Eva-4B-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54b5f33339a1f00461d34b13dd7184947a85a1de11a97fe05dfd9ced3d76b20b +size 2823710368 diff --git a/FutureMa_Eva-4B-Q6_K.gguf b/FutureMa_Eva-4B-Q6_K.gguf new file mode 100644 index 0000000..f98ff86 --- /dev/null +++ b/FutureMa_Eva-4B-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abe088bfbc408ce781fb40e175c288202bc6cf76ffba829aeddb1fb3ff0c6bf9 +size 3306260128 diff --git a/FutureMa_Eva-4B-Q6_K_L.gguf b/FutureMa_Eva-4B-Q6_K_L.gguf new file mode 100644 index 0000000..8077080 --- /dev/null +++ b/FutureMa_Eva-4B-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e133b2519810e877774d904086c37dbbcd52ce0340f5c75d73a20dc7fcfc522f +size 3400460448 diff --git a/FutureMa_Eva-4B-Q8_0.gguf b/FutureMa_Eva-4B-Q8_0.gguf new file mode 100644 index 0000000..4298eb5 --- /dev/null +++ b/FutureMa_Eva-4B-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf99354cc59572c0c4066a0e2a9f8b276651f80e1a198f014cb32a88b4f6c5d8 +size 4280404128 diff --git a/FutureMa_Eva-4B-bf16.gguf b/FutureMa_Eva-4B-bf16.gguf new file mode 100644 index 0000000..a1939b8 --- /dev/null +++ b/FutureMa_Eva-4B-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c952578afc5b1325f15c33751191b64ccf090e4838de31fa106993224f9e38aa +size 8051283872 diff --git a/FutureMa_Eva-4B-imatrix.gguf b/FutureMa_Eva-4B-imatrix.gguf new file mode 100644 index 0000000..d188f63 --- /dev/null +++ b/FutureMa_Eva-4B-imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d05e007862800d5969353396ce4a62ee6c1630b5a6e6506b26a19e391a5f17f5 +size 3872640 diff --git a/README.md b/README.md new file mode 100644 index 0000000..daabcfc --- /dev/null +++ b/README.md @@ -0,0 +1,190 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +tags: +- finance +- earnings-calls +- financial-nlp +- text-classification +- qwen3 +- llm-as-judge +- distillation +base_model_relation: quantized +base_model: FutureMa/Eva-4B +license: apache-2.0 +language: +- en +spaces: +- FutureMa/financial-evasion-detection +--- + +## Llamacpp imatrix Quantizations of Eva-4B by FutureMa + +Using llama.cpp release b7703 for quantization. + +Original model: https://huggingface.co/FutureMa/Eva-4B + +All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/82ae9b520227f57d79ba04add13d0d0d) + +Run them in your choice of tools: + +- [llama.cpp](https://github.com/ggml-org/llama.cpp) +- [LM Studio](https://lmstudio.ai/) +- [koboldcpp](https://github.com/LostRuins/koboldcpp) +- [Jan AI](https://www.jan.ai/) +- [Text Generation Web UI](https://github.com/oobabooga/text-generation-webui) +- [LoLLMs](https://github.com/ParisNeo/lollms) + +Note: if it's a newly supported model, you may need to wait for an update from the developers. + +## Prompt format + +``` +<|im_start|>system +{system_prompt}<|im_end|> +<|im_start|>user +{prompt}<|im_end|> +<|im_start|>assistant +``` + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [Eva-4B-bf16.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-bf16.gguf) | bf16 | 8.05GB | false | Full BF16 weights. | +| [Eva-4B-Q8_0.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-Q8_0.gguf) | Q8_0 | 4.28GB | false | Extremely high quality, generally unneeded but max available quant. | +| [Eva-4B-Q6_K_L.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-Q6_K_L.gguf) | Q6_K_L | 3.40GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [Eva-4B-Q6_K.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-Q6_K.gguf) | Q6_K | 3.31GB | false | Very high quality, near perfect, *recommended*. | +| [Eva-4B-Q5_K_L.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-Q5_K_L.gguf) | Q5_K_L | 2.98GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [Eva-4B-Q5_K_M.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-Q5_K_M.gguf) | Q5_K_M | 2.89GB | false | High quality, *recommended*. | +| [Eva-4B-Q5_K_S.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-Q5_K_S.gguf) | Q5_K_S | 2.82GB | false | High quality, *recommended*. | +| [Eva-4B-Q4_1.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-Q4_1.gguf) | Q4_1 | 2.60GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [Eva-4B-Q4_K_L.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-Q4_K_L.gguf) | Q4_K_L | 2.59GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [Eva-4B-Q4_K_M.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-Q4_K_M.gguf) | Q4_K_M | 2.50GB | false | Good quality, default size for most use cases, *recommended*. | +| [Eva-4B-Q4_K_S.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-Q4_K_S.gguf) | Q4_K_S | 2.38GB | false | Slightly lower quality with more space savings, *recommended*. | +| [Eva-4B-Q4_0.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-Q4_0.gguf) | Q4_0 | 2.38GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [Eva-4B-IQ4_NL.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-IQ4_NL.gguf) | IQ4_NL | 2.38GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [Eva-4B-Q3_K_XL.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-Q3_K_XL.gguf) | Q3_K_XL | 2.33GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [Eva-4B-IQ4_XS.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-IQ4_XS.gguf) | IQ4_XS | 2.27GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Eva-4B-Q3_K_L.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-Q3_K_L.gguf) | Q3_K_L | 2.24GB | false | Lower quality but usable, good for low RAM availability. | +| [Eva-4B-Q3_K_M.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-Q3_K_M.gguf) | Q3_K_M | 2.08GB | false | Low quality. | +| [Eva-4B-IQ3_M.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-IQ3_M.gguf) | IQ3_M | 1.96GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Eva-4B-Q3_K_S.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-Q3_K_S.gguf) | Q3_K_S | 1.89GB | false | Low quality, not recommended. | +| [Eva-4B-IQ3_XS.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-IQ3_XS.gguf) | IQ3_XS | 1.81GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Eva-4B-Q2_K_L.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-Q2_K_L.gguf) | Q2_K_L | 1.76GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [Eva-4B-IQ3_XXS.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-IQ3_XXS.gguf) | IQ3_XXS | 1.67GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [Eva-4B-Q2_K.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-Q2_K.gguf) | Q2_K | 1.67GB | false | Very low quality but surprisingly usable. | +| [Eva-4B-IQ2_M.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-IQ2_M.gguf) | IQ2_M | 1.51GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. | + +## Embed/output weights + +Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to. + +## Downloading using huggingface-cli + +
+ Click to view download instructions + +First, make sure you have hugginface-cli installed: + +``` +pip install -U "huggingface_hub[cli]" +``` + +Then, you can target the specific file you want: + +``` +huggingface-cli download bartowski/FutureMa_Eva-4B-GGUF --include "FutureMa_Eva-4B-Q4_K_M.gguf" --local-dir ./ +``` + +If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run: + +``` +huggingface-cli download bartowski/FutureMa_Eva-4B-GGUF --include "FutureMa_Eva-4B-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (FutureMa_Eva-4B-Q8_0) or download them all in place (./) + +
+ +## ARM/AVX information + +Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass. + +Now, however, there is something called "online repacking" for weights. details in [this PR](https://github.com/ggml-org/llama.cpp/pull/9921). If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly. + +As of llama.cpp build [b4282](https://github.com/ggml-org/llama.cpp/releases/tag/b4282) you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0. + +Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to [this PR](https://github.com/ggml-org/llama.cpp/pull/10541) which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase. + +
+ Click to view Q4_0_X_X information (deprecated + +I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking. + +
+ Click to view benchmarks on an AVX2 system (EPYC7702) + +| model | size | params | backend | threads | test | t/s | % (vs Q4_0) | +| ------------------------------ | ---------: | ---------: | ---------- | ------: | ------------: | -------------------: |-------------: | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp512 | 204.03 ± 1.03 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp1024 | 282.92 ± 0.19 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp2048 | 259.49 ± 0.44 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg128 | 39.12 ± 0.27 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg256 | 39.31 ± 0.69 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg512 | 40.52 ± 0.03 | 100% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp512 | 301.02 ± 1.74 | 147% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp1024 | 287.23 ± 0.20 | 101% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp2048 | 262.77 ± 1.81 | 101% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg128 | 18.80 ± 0.99 | 48% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg256 | 24.46 ± 3.04 | 83% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg512 | 36.32 ± 3.59 | 90% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp512 | 271.71 ± 3.53 | 133% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp1024 | 279.86 ± 45.63 | 100% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp2048 | 320.77 ± 5.00 | 124% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg128 | 43.51 ± 0.05 | 111% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg256 | 43.35 ± 0.09 | 110% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg512 | 42.60 ± 0.31 | 105% | + +Q4_0_8_8 offers a nice bump to prompt processing and a small bump to text generation + +
+ +
+ +## Which file should I choose? + +
+ Click here for details + +A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9) + +The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have. + +If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM. + +If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total. + +Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'. + +If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M. + +If you want to get more into the weeds, you can check out this extremely useful feature chart: + +[llama.cpp feature matrix](https://github.com/ggml-org/llama.cpp/wiki/Feature-matrix) + +But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size. + +These I-quants can also be used on CPU, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide. + +
+ +## Credits + +Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset. + +Thank you ZeroWw for the inspiration to experiment with embed/output. + +Thank you to LM Studio for sponsoring my work. + +Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file